documentprocessing’s gists

documentprocessing / extract-attachments-from-msg-file-extract-msg-python.py

Created May 8, 2024 14:50

Extract attachments from MSG file in Python

	import extract_msg

	# Specify the path to your .msg file
	msg_file_path = 'path/to/your/file.msg'
	# Specify the directory where attachments should be saved
	save_directory = 'path/to/save/attachments/'

	# Open the MSG file
	with extract_msg.openMsg(msg_file_path) as msg:
	# Loop through attachments

documentprocessing / read-message-properties-from-MSG-file.py

Created May 8, 2024 14:47

Read message details from MSG file

	import extract_msg
	# open message file
	msg = extract_msg.openMsg("input.msg")
	# print sender name
	print('Sender: {}'.format(msg.sender))
	# print date
	print('Sent On: {}'.format(msg.date))
	# print subject
	print('Subject: {}'.format(msg.subject))
	# print body

documentprocessing / extract-tables-from-pdf-pdf2docx.py

Last active April 27, 2024 09:38

Extract tables from PDF file using pdf2docx API

	from pdf2docx import Converter

	pdf_file = 'sample_pdf.pdf'

	converter = Converter(pdf_file)
	tables = converter.extract_tables(start=0, end=1)
	converter.close()

	#loop through the tables to print these
	for table in tables:

documentprocessing / convert-specific-pages-of-pdf-to-docx-pdf2docx.py

Created April 27, 2024 07:01

Convert specific PDF pages to DOCX using pdf2docx API in Python

	from pdf2docx import Converter

	# PDF file to be converted
	pdf_file = 'example.pdf'
	# Output DOCX file
	docx_file = 'output.docx'

	# Create a PDF to DOCX converter object
	cv = Converter(pdf_file)

documentprocessing / convert-pdf-to-docx-using-pdf2docx-api.py

Created April 27, 2024 06:53

Convert PDF files to DOCX with pdf2docx

	from pdf2docx import Converter

	# Specify the PDF file to convert
	pdf_file = 'example.pdf'
	docx_file = 'output.docx'

	# Create a Converter object and convert the PDF to DOCX
	cv = Converter(pdf_file)
	cv.convert(docx_file, start=0, end=None)
	cv.close()

documentprocessing / add-bullets-to-pptx-slide-wht-python-pptx.py

Created April 21, 2024 18:10

Add Bullets to PowerPoint PPTX

	from pptx import Presentation

	prs = Presentation()
	slide_with_bullet_layout = prs.slide_layouts[1]

	slide = prs.slides.add_slide(slide_with_bullet_layout)
	shapes = slide.shapes

	title_shape = shapes.title
	body_shape = shapes.placeholders[1]

documentprocessing / add-textbox-to-presentation-with-python-ptpx.py

Created April 21, 2024 18:08

Add Textbox to Presentation with python-pptx

	from pptx import Presentation
	from pptx.util import Inches, Pt

	presentation = Presentation()
	blank_slide_layout = presentation.slide_layouts[6]
	slide = presentation.slides.add_slide(blank_slide_layout)

	#set the dimensions of the text box
	left = top = width = height = Inches(1)
	txBox = slide.shapes.add_textbox(left, top, width, height)

documentprocessing / read-pptx.py

Created April 21, 2024 18:01

Read PPTX with python-pptx

	from pptx import Presentation

	presentation = Presentation('path_to_presentation_file.pptx')

	presentation.save('paht_to_updated_pptx_file.pptx')

documentprocessing / create-pptx-with-python-pptx.py

Last active April 21, 2024 18:02

Create PowerPoint PPTX with python-pptx

	# import Presentation class from python-pptx library
	from pptx import Presentation

	# Creating presentation object
	root_Presentation = Presentation()

	# Creating slide layout
	layout_slide = root_Presentation.slide_layouts[0]

	#Create a slide object and attach it to the Presentation

documentprocessing / udpate-existing-column-in-XLS-with-Pyexcel-XLS.py

Created March 26, 2024 19:11

Update existing Column in XLS file with Pyexcel-XLS

	import pyexcel as p

	#open a sample Excel file
	sheet = p.get_sheet(file_name="example.xls")

	#update data in existing column
	sheet.column[2] = ["Column 3", 100, 200, 300]

	#Save XLS file to disc
	sheet.save_as("updateexisting.xls")

Document Processing documentprocessing